code-review-ai-ai-review
You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C
28
21%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/code-review-ai-ai-review/SKILL.mdQuality
Discovery
14%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is truncated mid-sentence, rendering it incomplete and unusable for skill selection. Even the visible portion relies on vague buzzwords ('intelligent pattern recognition', 'modern DevOps practices') and uses second-person framing ('You are an expert') rather than describing concrete capabilities in third person. It lacks any explicit trigger guidance and would conflict with numerous other development-related skills.
Suggestions
Complete the truncated description and add an explicit 'Use when...' clause with natural trigger terms like 'review my code', 'PR review', 'pull request', 'code quality', 'find bugs'.
Replace abstract buzzwords ('intelligent pattern recognition', 'modern DevOps practices') with specific concrete actions such as 'Reviews pull requests for bugs, security vulnerabilities, and style issues' or 'Suggests code improvements and detects anti-patterns'.
Rewrite in third person voice ('Performs code reviews...') instead of second person ('You are an expert...') to match the expected format for skill descriptions.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions 'automated static analysis, intelligent pattern recognition, and modern DevOps practices' but these are abstract buzzwords rather than concrete actions. No specific actions like 'review pull requests', 'detect bugs', or 'suggest fixes' are listed. The description also appears truncated. | 1 / 3 |
Completeness | The description is truncated mid-sentence, so it fails to answer both 'what does this do' and 'when should Claude use it'. There is no 'Use when...' clause or equivalent trigger guidance, and the 'what' portion is vague buzzwords rather than concrete capabilities. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'code review', 'static analysis', 'GitHub Copilot', and 'DevOps', but the description is truncated and relies heavily on tool names and jargon rather than natural user phrases like 'review my code', 'PR review', or 'check for bugs'. | 2 / 3 |
Distinctiveness Conflict Risk | The description is extremely broad, covering 'code review', 'static analysis', 'pattern recognition', and 'DevOps practices', which could overlap with many other skills related to coding, CI/CD, testing, or general development assistance. | 1 / 3 |
Total | 5 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a sprawling reference document that tries to cover the entire domain of AI-powered code review in a single file. It suffers from severe verbosity, explaining well-known concepts (OWASP, SOLID, N+1 queries) that Claude already understands, and includes large code blocks that are illustrative rather than executable. The content would benefit enormously from being split into focused sub-files with a lean overview, and from replacing conceptual explanations with only the project-specific configuration and patterns Claude wouldn't already know.
Suggestions
Reduce the SKILL.md to a concise overview (~50-80 lines) covering the workflow steps and decision points, moving detailed code examples for security, performance, architecture, and CI/CD into separate referenced files.
Remove explanations of concepts Claude already knows (OWASP Top 10 descriptions, SOLID principle definitions, what N+1 queries are) and replace with only project-specific rules or thresholds.
Make code examples truly executable by implementing missing functions (e.g., `get_pr_diff()`, `to_github_comment()`, `detectsSharedDatabase`) or remove them in favor of concrete CLI commands and configuration snippets.
Add explicit validation checkpoints and error recovery steps to the workflow (e.g., what to do when static analysis tools fail, how to handle AI false positives, retry logic for API calls).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Explains concepts Claude already knows (OWASP Top 10 list, SOLID principles, what N+1 queries are). Includes multiple large code blocks across Python, TypeScript, Go, JavaScript, YAML, and Bash that are illustrative rather than executable. The 'Use this skill when / Do not use this skill when' sections are tautological filler. Time-sensitive model recommendations (GPT-5, Claude 4.5 Sonnet) add noise. | 1 / 3 |
Actionability | Contains substantial code examples that appear concrete, but most are pseudocode-level illustrations rather than truly executable (e.g., undefined functions like `detectsSharedDatabase`, `find_loops`, `reviewer.get_pr_diff()`, missing `to_github_comment()` method). The GitHub Actions workflow is the most actionable piece but references scripts that don't exist. The $ARGUMENTS placeholder is never defined. | 2 / 3 |
Workflow Clarity | The 'Automated Code Review Workflow' section provides a reasonable sequence (triage → static analysis → AI review → routing), and the CI/CD pipeline has a quality gate. However, there are no explicit validation checkpoints or error recovery steps between stages. The workflow lacks feedback loops for when AI review produces false positives or when static analysis tools fail. | 2 / 3 |
Progressive Disclosure | Monolithic wall of content with no bundle files to support it. References `resources/implementation-playbook.md` which doesn't exist. All content—architecture analysis, security detection, performance review, CI/CD integration, complete examples—is inlined into a single massive file with no meaningful separation or navigation structure. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
79d9c42
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.